Best analysis ever! Andres Rafael Tito

# Import the pandas and numpy packages
import pandas as pd
import numpy as np
# Load the data
dinosaurs = pd.read_csv('data/dinosaurs.csv')

# Preview the dataframe
dinosaurs.head()

# 1. How many different dinosaur names are present in the data?

# Number of unique dinosaur names
unique_dinosaur_names = dinosaurs['name'].nunique()
print(f"\n There are {unique_dinosaur_names} unique dinosaur names in the dataset.")

# 2. Which was the largest dinosaur? What about missing data in the dataset?

# Determine the largest dinosaur by length
largest_dinosaur = dinosaurs.loc[dinosaurs['length_m'].idxmax()]
print(f"\n The largest dinosaur by length has {largest_dinosaur['length_m']}.")

# Check for missing data
missing_data = dinosaurs.isnull().sum()
print(f"\n There are {missing_data['occurrence_no']} missing data.")

# 3. What dinosaur type has the most occurrences in this dataset? Create a visualization to display the number of dinosaurs per type. 

# Import the matplotlib and seaborn packages
import matplotlib.pyplot as plt
import seaborn as sns

# Count the occurrences of each dinosaur type
dinosaur_type_counts = dinosaurs['type'].value_counts()

# Create a bar chart
plt.figure(figsize = (10,6))
sns.barplot(x = dinosaur_type_counts.values, y = dinosaur_type_counts.index, palette = 'viridis')
plt.title('Number of dinosaurs per type')
plt.xlabel('Count')
plt.ylabel('Dinosaur type')
plt.show()

# Get the most frequent dinosaur type
most_dinosaur_type = dinosaur_type_counts.idxmax()
most_dinosaur_count = dinosaur_type_counts.max()
print(f"\n The most frequent dinosaur type is {most_dinosaur_type} with {most_dinosaur_count} occurrences.")

# 4. Did dinosaurs get bigger over time? Show the relation between the dinosaur length and their age to illustrate this.

# Create a scatterplot 
plt.figure(figsize = (10,6))
sns.scatterplot(data = dinosaurs, x = 'max_ma', y = 'length_m', hue = 'type', palette = 'viridis', alpha = 0.7)
plt.title('Dinosaur length over time')
plt.xlabel('Age (millions of years ago)')
plt.ylabel('Length (meters)')
plt.show()

# Import scipy packages
import numpy as np
from scipy.stats import linregress

# Perform linear regression 
valid_data = dinosaurs.dropna(subset=['max_ma', 'length_m'])
slope, intercept, r_value, p_value, std_error = linregress(valid_data['max_ma'], valid_data['length_m'])
print(f"\n Regression slope: {slope:.2f}")
print(f"\n P-value: {p_value:.2f}")
print(f"\n There is a significant relationship between the age and the length of dinosaurs due to age decreases (which means moving closer to the current time) as length increases. In conclusion, yes, the dinosaurs did indeed get bigger over time.")

# 5. Use the AI assitant to create an interactive map showing each record.

# Import folium package
import folium
from folium.plugins import MarkerCluster

# Calculate average coordinates for centering the map
average_lat = dinosaurs['lat'].mean()
average_lon = dinosaurs['lng'].mean()

# Create a base map
mymap = folium.Map(location = [average_lat, average_lon], zoom_start = 2)

# Initialize a MarkerCluster
marker_cluster = MarkerCluster().add_to(mymap)

# Add markers to the cluster
for idx, row in dinosaurs.iterrows():
    if pd.notnull(row['lat']) and pd.notnull(row['lng']):
        folium.Marker(location = [row['lat'], row['lng']],
                      popup=f"Name: {row['name']}<br>Type: {row['type']}<br>Length: {row['length_m']} m").add_to(marker_cluster)

# Save the map to an HTML file and show it
mymap.save('dinosaur_map.html')
mymap

# 6. Distribution of dinosaur lengths
plt.figure(figsize=(10, 6))
sns.histplot(dinosaurs['length_m'].dropna(), bins=30, kde=True, color='blue')
plt.title('Distribution of Dinosaur Lengths')
plt.xlabel('Length (meters)')
plt.ylabel('Frequency')
plt.show()
print(f"\n The histograms show the frequency of dinosaurs for different length ranges and the KDE line provides a smooth estimate of the distribution, helping to identify trends more clearly.")